Pengyu Wang

Privacy (1)

large language model (12) reinforcement learning from human feedback (3) multi-modal learning (3) direct preference optimization (2) representation learning (2) intent classification (2) convolution neural network (2) out-of-domain detection (2) inference-time alignment (2) speech generation (2) self-supervised learning (2) bayesian inference (2) source localization (2) text classification (2) multimodal large language model (2) natural language processing (1) multi-task learning (1) ensemble learning (1) benchmark evaluation (1) transfer learning (1)